When Reconstruction Is Not Enough: Doubly Robust Counterfactual and Interventional Mediation Analysis with Learned Multimodal Representations

arXiv:2610.30220v1 Announce Type: new Abstract: Learned representations of high-dimensional multimodal health records are increasingly used to adjust for confounding, yet they are usually trained to reconstruct the data rather than preserve the information that causal identification requires. We st…

Read the full story at arXiv cs.LG ↗

Timeline · 1 report

1. 2026-10-23 04:00 · arXiv cs.LG
   When Reconstruction Is Not Enough: Doubly Robust Counterfactual and Interventional Mediation Analysis with Learned Multimodal Representations